mlsanityData to 14 Oct 2026

TransCut: Transparent Object Segmentation from a Light-Field Image

arXiv 1511.06853 ↗First posted 21 Nov 2015cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

The segmentation of transparent objects can be very useful in computer vision applications. However, because they borrow texture from their background and have a similar appearance to their surroundings, transparent objects are not handled well by regular image segmentation methods. We propose a method that overcomes these problems using the consistency and distortion properties of a light-field image. Graph-cut optimization is applied for the pixel labeling problem. The light-field linearity is used to estimate the likelihood of a pixel belonging to the transparent object or Lambertian background, and the occlusion detector is used to find the occlusion boundary. We acquire a light field dataset for the transparent object, and use this dataset to evaluate our method. The results demonstrate that the proposed method successfully segments transparent objects from the background.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 7; 2024: 3; 2025: 4; 2026: 2.

27 papers.

Sort:

By area:

  1. 2021Concealed Object Detectioncited by 212
  2. 2022ClearPose: Large-scale Transparent Object Dataset and Benchmarkcited by 46
  3. 2022Glass Segmentation with RGB-Thermal Image Pairscited by 26
  4. 2023RFENet: Towards Reciprocal Feature Evolution for Glass Segmentationcited by 19
  5. 2023TRansPose: Large-Scale Multispectral Dataset for Transparent Objectcited by 15
  6. 2021Segmenting Transparent Object in the Wild with Transformercited by 13
  7. 2022TransNet: Category-Level Transparent Object Pose Estimationcited by 13
  8. 2024LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flowcited by 11
  9. 2022Self-supervised Transparent Liquid Segmentation for Robotic Pouringcited by 10
  10. 2025Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimationcited by 8
  11. 2021FakeMix Augmentation Improves Transparent Object Detectioncited by 7
  12. 2025Deep Learning in Concealed Dense Predictioncited by 6
15 more
  1. 2022Trans2k: Unlocking the Power of Deep Models for Transparent Object Trackingcited by 4
  2. 2024A New Dataset and a Distractor-Aware Architecture for Transparent Object Trackingcited by 4
  3. 2023GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Modelscited by 3
  4. 2023Learning Kernel-Modulated Neural Representation for Efficient Light Field Compressioncited by 2
  5. 2021A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Environmental Microorganism Images: from Convolutional Neural Networks to Visual Transformerscited by 1
  6. 2022Grasping the Inconspicuouscited by 1
  7. 2023TransNet: Transparent Object Manipulation Through Category-Level Pose Estimationcited by 1
  8. 2023Transparent Object Tracking with Enhanced Fusion Modulecited by 1
  9. 2024Influence of Water Droplet Contamination for Transparency Segmentationcited by 1
  10. 2021Refractive Light-Field Features for Curved Transparent Objects in Structure from Motioncited by 0
  11. 2023Learning-based Spatial and Angular Information Separation for Light Field Compressioncited by 0
  12. 2025Semantic Segmentation of Transparent and Opaque Drinking Glasses with the Help of Zero-shot Learningcited by 0
  13. 2025Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagerycited by 0
  14. 2026Transparent Fragments Contour Estimation via Visual-Tactile Fusion for Autonomous Reassemblycited by 0
  15. 2026SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Groupingcited by 0